The Blog

the "The" will stay, anything else might change

Relative Entropy Pathwise Policy Optimization - Technical Overview

A lightweight overview of the new REPPO algorithm

21 min read · October 02, 2025

2025 · rl algorithms
REPPO - Why build a new algorithm

A tongue-in-cheek history of REPPO

6 min read · October 02, 2025

2025 · rl algorithms humor · papers
Loss Functions and Calibration

Reminder to post about CVAML

1 min read · July 21, 2025

2025 · technical rl · papers
Reward Design and Termination

Understanding the interplay between reward design, termination, and truncation in RL

11 min read · July 20, 2025

2025 · basics rl